Upload tokenizer

README.md

@@ -1,7 +1,7 @@
 ---
+base_model: gpt2
 library_name: transformers
 license: mit
-base_model: gpt2
 tags:
 - generated_from_trainer
 model-index:

added_tokens.json

@@ -0,0 +1,2277 @@
+{
+  "\n": 52299,
+  " ": 50951,
+  " 0": 52220,
+  " 00": 51520,
+  " 1": 51310,
+  " 10": 52322,
+  " 14": 52002,
+  " 2": 51015,
+  " 20": 50981,
+  " 201": 50749,
+  " 3": 51512,
+  " 30": 52296,
+  " 4": 51850,
+  " 40": 52136,
+  " 5": 50693,
+  " 50": 51095,
+  " 6": 51317,
+  " 7": 50907,
+  " 8": 50528,
+  " 9": 51168,
+  " 93": 52428,
+  " 97": 51495,
+  " a": 51102,
+  " aal": 51786,
+  " aala": 51807,
+  " ab": 52312,
+  " abon": 50855,
+  " ach": 51515,
+  " acha": 52276,
+  " ad": 50875,
+  " af": 52110,
+  " afri": 52436,
+  " africain": 52281,
+  " ah": 51609,
+  " ahla": 51651,
+  " ahna": 50554,
+  " ahsen": 51365,
+  " aj": 51370,
+  " ak": 52148,
+  " aka": 51714,
+  " akbar": 52032,
+  " akber": 51672,
+  " akh": 51656,
+  " akid": 51313,
+  " akthar": 51791,
+  " akther": 51431,
+  " al": 51785,
+  " ala": 51324,
+  " ale": 51271,
+  " alech": 52027,
+  " alex": 52085,
+  " alexis": 50280,
+  " alf": 51854,
+  " alg": 52244,
+  " alger": 52197,
+  " ali": 50891,
+  " alih": 52432,
+  " aliha": 51698,
+  " alik": 52191,
+  " alikom": 50594,
+  " alina": 52152,
+  " alla": 50721,
+  " am": 52452,
+  " ama": 50386,
+  " amal": 51068,
+  " aman": 52006,
+  " amana": 51797,
+  " ame": 51665,
+  " amin": 52176,
+  " amine": 50775,
+  " amma": 52005,
+  " an": 51958,
+  " and": 50436,
+  " andou": 50960,
+  " ani": 51053,
+  " anna": 52266,
+  " anni": 50781,
+  " ans": 51708,
+  " anta": 50938,
+  " anti": 51897,
+  " ar": 51020,
+  " are": 50711,
+  " as": 50372,
+  " ass": 51859,
+  " at": 50784,
+  " ata": 50345,
+  " ataw": 51628,
+  " atta": 52076,
+  " au": 52200,
+  " aussi": 50264,
+  " av": 51816,
+  " avant": 50759,
+  " avec": 51529,
+  " aw": 50328,
+  " awel": 51434,
+  " awled": 50547,
+  " ay": 51345,
+  " aya": 51352,
+  " az": 50401,
+  " b": 51906,
+  " ba": 50737,
+  " baarcha": 50468,
+  " baba": 51673,
+  " bache": 51712,
+  " bachir": 51238,
+  " bad": 52511,
+  " bah": 52373,
+  " bahi": 50478,
+  " bal": 50922,
+  " ban": 51663,
+  " bar": 52009,
+  " bara": 51667,
+  " barch": 52034,
+  " bark": 51533,
+  " barka": 52325,
+  " barnamej": 51203,
+  " barnem": 50956,
+  " barnemej": 50597,
+  " barra": 50892,
+  " bas": 50690,
+  " bassem": 51623,
+  " bat": 52388,
+  " bay": 50571,
+  " baya": 50656,
+  " baz": 50758,
+  " bb": 50865,
+  " bch": 50596,
+  " be": 52340,
+  " beau": 52423,
+  " beb": 51316,
+  " bech": 50316,
+  " beche": 50842,
+  " bed": 51788,
+  " beh": 50618,
+  " beha": 51857,
+  " behi": 50873,
+  " behya": 52092,
+  " bej": 50261,
+  " beji": 50537,
+  " bek": 51149,
+  " bel": 52352,
+  " belehi": 50832,
+  " belek": 52361,
+  " bellahi": 51728,
+  " belle": 52093,
+  " bellehi": 51738,
+  " ben": 51080,
+  " bent": 51912,
+  " benzarti": 51297,
+  " ber": 52044,
+  " berasmi": 51860,
+  " bes": 52503,
+  " bet": 51968,
+  " bey": 52454,
+  " bez": 52434,
+  " bhi": 50560,
+  " bhim": 51125,
+  " bi": 51935,
+  " bich": 51894,
+  " bid": 51314,
+  " bien": 51012,
+  " big": 52293,
+  " bih": 51870,
+  " biha": 51632,
+  " bihom": 52011,
+  " bik": 52039,
+  " bikom": 51173,
+  " bil": 52218,
+  " billahi": 52528,
+  " bin": 52377,
+  " bina": 52305,
+  " bir": 51960,
+  " bis": 51067,
+  " bit": 50484,
+  " bjeh": 52216,
+  " bk": 51700,
+  " bkhir": 50584,
+  " bkol": 50483,
+  " bl": 51778,
+  " bla": 50957,
+  " blad": 52368,
+  " blas": 50416,
+  " blech": 51875,
+  " bled": 51060,
+  " bledi": 52488,
+  " bledna": 51235,
+  " bli": 51952,
+  " bn": 50291,
+  " bo": 51668,
+  " bon": 51463,
+  " bonne": 51973,
+  " bor": 50491,
+  " bos": 51694,
+  " bou": 51739,
+  " bouh": 50539,
+  " bouk": 50732,
+  " boun": 50578,
+  " bour": 51671,
+  " boutoula": 52213,
+  " bouzid": 51458,
+  " br": 51669,
+  " bra": 50439,
+  " brabbi": 51470,
+  " bras": 50795,
+  " brav": 50811,
+  " bravobravo": 50694,
+  " bro": 52141,
+  " bsara": 50673,
+  " bu": 50605,
+  " bureau": 52182,
+  " by": 52372,
+  " bz": 52351,
+  " c": 51938,
+  " ca": 50740,
+  " cab": 50590,
+  " car": 50630,
+  " cas": 50808,
+  " ce": 51639,
+  " cette": 50684,
+  " ch": 50894,
+  " cha": 50933,
+  " chaab": 51646,
+  " chab": 51250,
+  " chad": 51750,
+  " chai": 50866,
+  " chaine": 50387,
+  " chal": 50820,
+  " cham": 52116,
+  " champi": 52358,
+  " chan": 50459,
+  " chance": 51680,
+  " char": 50858,
+  " chay": 52179,
+  " chbih": 51573,
+  " chbik": 50835,
+  " che": 52320,
+  " cheb": 51886,
+  " ched": 50806,
+  " cher": 51716,
+  " chey": 50890,
+  " chi": 51802,
+  " chib": 52375,
+  " chiboub": 52008,
+  " chkon": 50429,
+  " chkoun": 50702,
+  " chma": 51764,
+  " chmage": 50964,
+  " chn": 50391,
+  " chnia": 50517,
+  " chniya": 50359,
+  " chnouwa": 51049,
+  " chnowa": 51177,
+  " cho": 50700,
+  " chof": 51488,
+  " chok": 51494,
+  " chou": 50846,
+  " chouf": 50622,
+  " choufou": 51832,
+  " chw": 51781,
+  " chwa": 50381,
+  " chway": 50977,
+  " chwaya": 50949,
+  " chy": 50699,
+  " cla": 50360,
+  " clip": 51681,
+  " club": 51081,
+  " clubis": 52109,
+  " clubiste": 52401,
+  " clubistia": 52067,
+  " co": 52462,
+  " com": 52051,
+  " comm": 50975,
+  " comme": 51192,
+  " commenta": 52263,
+  " comp": 51447,
+  " con": 50322,
+  " cont": 51174,
+  " continu": 51737,
+  " continuation": 51374,
+  " contre": 52291,
+  " cor": 51162,
+  " cou": 52476,
+  " courage": 50420,
+  " cpr": 52004,
+  " cs": 50626,
+  " cu": 51841,
+  " cv": 51697,
+  " d": 50569,
+  " da": 51457,
+  " dab": 52183,
+  " dak": 52514,
+  " dakh": 50667,
+  " dam": 51795,
+  " dandouk": 51382,
+  " dans": 51481,
+  " dar": 51133,
+  " daw": 52145,
+  " dawla": 50617,
+  " day": 52425,
+  " dayma": 50279,
+  " de": 50281,
+  " dega": 51161,
+  " degaage": 51433,
+  " degag": 51789,
+  " degage": 51260,
+  " denya": 50883,
+  " der": 50948,
+  " des": 51613,
+  " dey": 51072,
+  " dgage": 51873,
+  " dh": 50880,
+  " dha": 52169,
+  " dhar": 50398,
+  " dhaw": 51059,
+  " di": 50648,
+  " din": 52026,
+  " dina": 52123,
+  " dinar": 51124,
+  " dire": 52038,
+  " dis": 51717,
+  " dislike": 51901,
+  " dit": 50698,
+  " dja": 51521,
+  " djabou": 50421,
+  " do": 51516,
+  " donc": 50445,
+  " dou": 51091,
+  " dr": 51418,
+  " dra": 51065,
+  " du": 52225,
+  " dz": 50841,
+  " e": 51287,
+  " eb": 52174,
+  " ech": 51443,
+  " echa": 51676,
+  " echkoun": 51268,
+  " ed": 50580,
+  " ef": 50723,
+  " efriki": 52236,
+  " eh": 52446,
+  " ej": 51279,
+  " eja": 51299,
+  " ejam": 51207,
+  " ejjam": 50671,
+  " ek": 52525,
+  " el": 51146,
+  " ela": 50720,
+  " elb": 51782,
+  " elba": 51295,
+  " elf": 51635,
+  " elfa": 50388,
+  " elg": 51858,
+  " eljam": 50588,
+  " elk": 50383,
+  " elkol": 51793,
+  " ella": 50792,
+  " elm": 52331,
+  " elma": 52308,
+  " elmou": 51353,
+  " elwa": 50510,
+  " ely": 51645,
+  " em": 52206,
+  " ema": 51740,
+  " emta": 51977,
+  " en": 51892,
+  " ena": 51393,
+  " enchallah": 50374,
+  " enes": 51687,
+  " eni": 51825,
+  " enn": 52439,
+  " enna": 50565,
+  " ennahdha": 51275,
+  " ennes": 52112,
+  " ensen": 51670,
+  " ent": 51127,
+  " enta": 52159,
+  " enti": 52402,
+  " entouma": 51804,
+  " enty": 51484,
+  " equipe": 50980,
+  " er": 50523,
+  " era": 52107,
+  " erajel": 50887,
+  " erjel": 50963,
+  " err": 50572,
+  " errajel": 51688,
+  " es": 52130,
+  " ess": 52449,
+  " essa": 52139,
+  " est": 50335,
+  " et": 52424,
+  " eta": 52270,
+  " etta": 51509,
+  " ettoun": 50344,
+  " ew": 51718,
+  " ex": 51197,
+  " ey": 51465,
+  " ez": 52264,
+  " f": 51452,
+  " fa": 51390,
+  " fac": 51752,
+  " fach": 50627,
+  " fad": 52520,
+  " fadina": 50978,
+  " fah": 52502,
+  " faha": 51703,
+  " faire": 52137,
+  " fait": 50287,
+  " fak": 51826,
+  " fal": 50830,
+  " fam": 51191,
+  " fama": 52393,
+  " famma": 51187,
+  " fan": 52052,
+  " far": 50689,
+  " fara": 52269,
+  " fare": 51925,
+  " fas": 51082,
+  " fat": 51606,
+  " faw": 50356,
+  " fay": 52240,
+  " fdha": 51835,
+  " fe": 50828,
+  " fech": 51099,
+  " fed": 50407,
+  " feh": 51026,
+  " feha": 51581,
+  " fehom": 52262,
+  " fehri": 51236,
+  " fek": 51715,
+  " fel": 51280,
+  " fem": 52282,
+  " fer": 51041,
+  " fes": 52345,
+  " fet": 51775,
+  " fhem": 51889,
+  " fi": 52150,
+  " fib": 51545,
+  " fih": 50924,
+  " fik": 51028,
+  " fikom": 52279,
+  " fil": 50567,
+  " film": 50805,
+  " fin": 51373,
+  " fina": 50882,
+  " fl": 52122,
+  " flou": 52049,
+  " flous": 51986,
+  " fo": 51005,
+  " fom": 52384,
+  " foot": 50461,
+  " for": 50672,
+  " forza": 51508,
+  " fou": 51725,
+  " fr": 51677,
+  " fran": 50998,
+  " franca": 51608,
+  " france": 52089,
+  " from": 52315,
+  " fu": 51144,
+  " fy": 51423,
+  " g": 50520,
+  " ga": 50849,
+  " gad": 50780,
+  " gafsa": 51658,
+  " gal": 51763,
+  " gar": 50935,
+  " gh": 51231,
+  " gha": 51077,
+  " ghal": 52385,
+  " ghalia": 50320,
+  " ghar": 51336,
+  " ghir": 50774,
+  " go": 52367,
+  " going": 51038,
+  " good": 51209,
+  " gran": 50495,
+  " grand": 52021,
+  " gu": 51167,
+  " h": 51941,
+  " ha": 50574,
+  " hab": 50595,
+  " hach": 51878,
+  " had": 50380,
+  " hada": 51105,
+  " hadh": 52526,
+  " hadha": 50355,
+  " hadhi": 52035,
+  " hadi": 51510,
+  " hahaha": 52477,
+  " hahahahaha": 51546,
+  " haj": 50807,
+  " haja": 50839,
+  " hak": 52010,
+  " hal": 51367,
+  " hala": 51141,
+  " ham": 50902,
+  " hamdi": 52337,
+  " han": 50466,
+  " hana": 51062,
+  " hani": 51604,
+  " har": 52100,
+  " has": 52353,
+  " hasbouna": 51817,
+  " hat": 51253,
+  " hata": 52304,
+  " hathi": 51642,
+  " hatta": 51773,
+  " haw": 51462,
+  " hay": 51502,
+  " haya": 50785,
+  " haz": 50426,
+  " he": 50563,
+  " hed": 50293,
+  " heda": 51291,
+  " hedha": 50946,
+  " hedhi": 51655,
+  " hedi": 50397,
+  " hek": 52327,
+  " heka": 51710,
+  " hel": 50941,
+  " het": 52033,
+  " hetha": 52344,
+  " hethi": 50404,
+  " heya": 51213,
+  " hez": 51720,
+  " hi": 51754,
+  " hia": 52513,
+  " hiwar": 50533,
+  " hiya": 51979,
+  " hmd": 51498,
+  " ho": 50606,
+  " hob": 52227,
+  " hom": 51436,
+  " homa": 51389,
+  " hor": 51453,
+  " hot": 51052,
+  " hou": 51288,
+  " houa": 51009,
+  " houwa": 52328,
+  " howa": 50797,
+  " hram": 52016,
+  " hta": 52073,
+  " hya": 51518,
+  " i": 51126,
+  " ia": 51527,
+  " ib": 51194,
+  " ich": 52489,
+  " icha": 51327,
+  " iched": 51614,
+  " id": 51107,
+  " idara": 51690,
+  " idha": 50664,
+  " if": 52355,
+  " ifri": 52492,
+  " ih": 51649,
+  " iheb": 51751,
+  " ij": 52349,
+  " ija": 52334,
+  " iji": 50608,
+  " ik": 51375,
+  " ikoun": 51505,
+  " il": 50782,
+  " ila": 51969,
+  " ilayhi": 50402,
+  " ilkol": 52410,
+  " illa": 51899,
+  " illi": 52392,
+  " im": 50869,
+  " ima": 51229,
+  " in": 52037,
+  " ina": 51384,
+  " inchalah": 50323,
+  " inik": 50992,
+  " inna": 51420,
+  " int": 51814,
+  " inta": 52420,
+  " inti": 52015,
+  " ir": 51547,
+  " is": 51530,
+  " isa": 52163,
+  " it": 52329,
+  " ita": 50675,
+  " itha": 50399,
+  " iz": 52208,
+  " j": 51309,
+  " ja": 52418,
+  " jab": 51221,
+  " jabri": 50848,
+  " jad": 51611,
+  " jah": 50485,
+  " jaime": 50338,
+  " jam": 50686,
+  " jama": 52014,
+  " jamais": 52250,
+  " jami": 51993,
+  " jan": 51097,
+  " jar": 50900,
+  " jaw": 52307,
+  " jay": 52510,
+  " jd": 52289,
+  " jdid": 50544,
+  " jdida": 51916,
+  " je": 50877,
+  " jeb": 52160,
+  " jed": 51861,
+  " jedou": 52422,
+  " jem": 52521,
+  " jemla": 51335,
+  " jen": 50409,
+  " jer": 52230,
+  " jet": 51852,
+  " jey": 51400,
+  " ji": 52472,
+  " jib": 50836,
+  " jit": 50403,
+  " jm": 51388,
+  " jma": 51948,
+  " jme": 50619,
+  " jo": 51328,
+  " job": 50704,
+  " jom": 51727,
+  " jomhour": 50644,
+  " jor": 52414,
+  " jou": 51108,
+  " jouer": 52332,
+  " joueret": 51216,
+  " joueur": 51061,
+  " joum": 50696,
+  " joumhour": 51368,
+  " jour": 51128,
+  " jus": 51034,
+  " just": 52278,
+  " juste": 50303,
+  " k": 51863,
+  " ka": 50921,
+  " kab": 50761,
+  " kad": 50444,
+  " kaf": 51403,
+  " kais": 50373,
+  " kal": 50895,
+  " kalb": 52162,
+  " kaleb": 52450,
+  " kam": 50709,
+  " kamcha": 50283,
+  " kamel": 51507,
+  " kan": 51176,
+  " kana": 50929,
+  " kar": 50375,
+  " kara": 51988,
+  " kas": 51223,
+  " kat": 51572,
+  " kaw": 51584,
+  " kay": 50474,
+  " kbal": 52259,
+  " kbir": 50396,
+  " kbira": 51674,
+  " ke": 50735,
+  " ked": 52342,
+  " keep": 50989,
+  " kef": 50982,
+  " kel": 50674,
+  " kelma": 50918,
+  " kem": 51340,
+  " kemla": 52078,
+  " ken": 51565,
+  " ker": 52287,
+  " kh": 51439,
+  " kha": 50826,
+  " khal": 50257,
+  " khali": 50575,
+  " khar": 50417,
+  " khater": 50719,
+  " khaw": 50348,
+  " khed": 51164,
+  " khi": 51056,
+  " khir": 51409,
+  " kho": 50727,
+  " khou": 50521,
+  " khouya": 50278,
+  " khoya": 52198,
+  " ki": 52341,
+  " kif": 50643,
+  " kifach": 51361,
+  " kifech": 52444,
+  " kifek": 50899,
+  " kifou": 52047,
+  " kil": 52419,
+  " king": 52192,
+  " kir": 51376,
+  " klam": 50333,
+  " klay": 50910,
+  " kleb": 51734,
+  " klem": 51071,
+  " klm": 52203,
+  " kn": 52181,
+  " ko": 50655,
+  " kol": 52079,
+  " kolha": 51332,
+  " kolhom": 51343,
+  " kolna": 51819,
+  " kon": 50294,
+  " kont": 52207,
+  " kor": 51562,
+  " korsi": 50361,
+  " kou": 50307,
+  " kouki": 50967,
+  " koul": 50339,
+  " koun": 51733,
+  " koura": 50683,
+  " kra": 52459,
+  " krah": 51974,
+  " l": 51089,
+  " la": 50983,
+  " labes": 51079,
+  " lah": 51046,
+  " lakin": 51269,
+  " lam": 52050,
+  " lan": 50629,
+  " las": 50337,
+  " law": 52058,
+  " lay": 50438,
+  " laz": 51285,
+  " lazem": 52165,
+  " lazim": 51195,
+  " lb": 51939,
+  " lba": 52193,
+  " lbled": 52271,
+  " lc": 52506,
+  " lclub": 51000,
+  " le": 50791,
+  " leb": 51428,
+  " lebes": 51123,
+  " leblad": 50352,
+  " lebled": 51985,
+  " leclub": 52117,
+  " lef": 51284,
+  " leflous": 50295,
+  " lefri": 51883,
+  " leh": 50502,
+  " lek": 50456,
+  " leklem": 50901,
+  " lel": 51118,
+  " lem": 51435,
+  " ler": 50527,
+  " les": 50767,
+  " let": 51004,
+  " lez": 51421,
+  " lezem": 52395,
+  " lf": 51756,
+  " lfri": 50431,
+  " lg": 51211,
+  " lha": 52125,
+  " li": 52013,
+  " lib": 51408,
+  " libled": 50984,
+  " libya": 52156,
+  " lif": 52413,
+  " lifri": 51682,
+  " lifriki": 51412,
+  " lih": 50743,
+  " lik": 51534,
+  " like": 51321,
+  " likom": 50944,
+  " lil": 50410,
+  " lim": 50872,
+  " lin": 51113,
+  " lina": 50945,
+  " lis": 51957,
+  " lit": 51110,
+  " lk": 50772,
+  " lkol": 51811,
+  " ll": 52309,
+  " lm": 51429,
+  " lma": 52288,
+  " lmar": 50443,
+  " lmo": 51864,
+  " lo": 52084,
+  " lok": 52490,
+  " lol": 52007,
+  " lom": 51456,
+  " lool": 51501,
+  " lot": 50301,
+  " lotfi": 50591,
+  " lou": 50681,
+  " louled": 51298,
+  " love": 50908,
+  " ls": 50613,
+  " lu": 50469,
+  " lw": 50304,
+  " lwa": 52258,
+  " ly": 51661,
+  " lyoum": 50745,
+  " m": 51417,
+  " ma": 50385,
+  " maak": 51867,
+  " mab": 50272,
+  " mach": 51893,
+  " macha": 50757,
+  " machallah": 50817,
+  " machari": 50259,
+  " machi": 50513,
+  " machrou": 50390,
+  " mad": 51450,
+  " mada": 52357,
+  " madam": 50813,
+  " madem": 50676,
+  " madh": 50475,
+  " maf": 51243,
+  " mafam": 50881,
+  " mafama": 50715,
+  " mafamech": 50833,
+  " mah": 50506,
+  " mahich": 52030,
+  " mahou": 52081,
+  " mahouch": 51330,
+  " mai": 51008,
+  " mais": 50763,
+  " maj": 52087,
+  " mak": 50341,
+  " makech": 52343,
+  " makh": 51471,
+  " mal": 50798,
+  " malla": 51397,
+  " malyoun": 51556,
+  " mam": 50370,
+  " man": 50768,
+  " mana": 52113,
+  " manich": 52397,
+  " mar": 51900,
+  " mara": 51561,
+  " marbou": 51840,
+  " mariem": 50638,
+  " maroc": 50677,
+  " marra": 50668,
+  " martou": 51018,
+  " mary": 50347,
+  " marzou": 51025,
+  " marzouki": 51103,
+  " mas": 51564,
+  " masa": 51073,
+  " masla": 50476,
+  " mass": 50566,
+  " mat": 51323,
+  " mata": 51783,
+  " match": 51634,
+  " math": 52120,
+  " matha": 50682,
+  " maw": 51637,
+  " mawjou": 51246,
+  " max": 50300,
+  " may": 52406,
+  " maya": 51552,
+  " maz": 50313,
+  " mba": 52455,
+  " mch": 52260,
+  " mcha": 50275,
+  " mchit": 51709,
+  " mda": 51092,
+  " me": 50649,
+  " mech": 50762,
+  " mechi": 51024,
+  " med": 50524,
+  " mef": 51647,
+  " meh": 50636,
+  " mej": 51069,
+  " mek": 51934,
+  " mel": 50589,
+  " mela": 51812,
+  " meli": 51372,
+  " mella": 50928,
+  " melli": 52129,
+  " men": 51398,
+  " mena": 51300,
+  " menek": 50473,
+  " menha": 50680,
+  " menhom": 50550,
+  " menou": 52389,
+  " mer": 50463,
+  " merci": 52380,
+  " mes": 51872,
+  " meskina": 51531,
+  " messa": 50486,
+  " met": 51946,
+  " mey": 51553,
+  " mez": 50940,
+  " mezel": 50450,
+  " mi": 52408,
+  " mib": 50970,
+  " miboun": 50730,
+  " mich": 51171,
+  " mil": 52166,
+  " mili": 51828,
+  " milli": 52064,
+  " mim": 52256,
+  " min": 52319,
+  " mina": 52383,
+  " minha": 51909,
+  " minhom": 51589,
+  " minou": 51170,
+  " mis": 51706,
+  " mit": 50549,
+  " miz": 51413,
+  " mka": 50971,
+  " mkach": 51044,
+  " mkacha": 51784,
+  " ml": 50586,
+  " mla": 50639,
+  " mle": 51322,
+  " mli": 51410,
+  " mn": 51902,
+  " mna": 51249,
+  " mnay": 52463,
+  " mnayek": 52411,
+  " mnin": 51524,
+  " mo": 50987,
+  " moch": 50809,
+  " mohamed": 51087,
+  " moin": 50879,
+  " mom": 51442,
+  " mon": 51777,
+  " moncef": 50543,
+  " monsieur": 51517,
+  " monta": 52065,
+  " mor": 51796,
+  " mos": 50405,
+  " mosta": 52069,
+  " mou": 52157,
+  " mouch": 51580,
+  " mouf": 52180,
+  " moufida": 51262,
+  " moun": 51705,
+  " mouna": 50864,
+  " mous": 51040,
+  " mout": 50714,
+  " mr": 51437,
+  " mra": 51369,
+  " ms": 51232,
+  " msa": 50959,
+  " mt": 51422,
+  " mta": 51982,
+  " mte": 51427,
+  " mu": 51290,
+  " mwa": 52072,
+  " my": 52415,
+  " mz": 51987,
+  " n": 52301,
+  " na": 50822,
+  " nab": 50266,
+  " nabara": 51947,
+  " nadh": 51759,
+  " nadi": 51570,
+  " naf": 50332,
+  " nafs": 51359,
+  " nah": 52131,
+  " nahdha": 51325,
+  " naj": 51240,
+  " nak": 51257,
+  " nal": 51790,
+  " nar": 51643,
+  " nas": 51311,
+  " naw": 51932,
+  " nay": 50314,
+  " nayek": 52484,
+  " nch": 52456,
+  " nchala": 51755,
+  " nchalah": 51302,
+  " nchalla": 50624,
+  " nchlh": 51147,
+  " nchouf": 51224,
+  " nchoufou": 52080,
+  " ne": 51953,
+  " neb": 51338,
+  " nef": 50532,
+  " neh": 50534,
+  " neji": 51265,
+  " nek": 52185,
+  " nenta": 50516,
+  " nes": 52509,
+  " nesma": 51551,
+  " net": 50499,
+  " nh": 52223,
+  " nha": 52077,
+  " nheb": 52254,
+  " nhebou": 50691,
+  " nhib": 51111,
+  " ni": 51876,
+  " nid": 52529,
+  " nik": 50746,
+  " nikom": 50538,
+  " nis": 50628,
+  " nit": 51557,
+  " nmout": 51620,
+  " nn": 50467,
+  " no": 51630,
+  " non": 50733,
+  " nor": 50530,
+  " normal": 50369,
+  " nos": 50995,
+  " not": 52224,
+  " notre": 50862,
+  " nou": 51800,
+  " nous": 51566,
+  " ns": 50458,
+  " nsa": 52063,
+  " nt": 51686,
+  " nta": 51178,
+  " o": 52501,
+  " of": 52151,
+  " oi": 52140,
+  " ok": 52043,
+  " okh": 50440,
+  " okhra": 52147,
+  " om": 51928,
+  " omek": 52234,
+  " omha": 52155,
+  " omhom": 51998,
+  " omik": 52239,
+  " omk": 52453,
+  " omkom": 52347,
+  " ommek": 52053,
+  " omo": 50464,
+  " omou": 51294,
+  " on": 52473,
+  " or": 50325,
+  " os": 52211,
+  " ou": 51903,
+  " oui": 52350,
+  " oum": 51992,
+  " ow": 50736,
+  " p": 52378,
+  " pa": 50265,
+  " page": 51254,
+  " par": 51827,
+  " parc": 52273,
+  " parti": 50451,
+  " pas": 50327,
+  " patron": 52324,
+  " pe": 52470,
+  " per": 51184,
+  " pf": 50991,
+  " ph": 51801,
+  " pi": 52404,
+  " pla": 52252,
+  " play": 50393,
+  " plu": 50509,
+  " plus": 50985,
+  " plz": 50472,
+  " po": 50752,
+  " poli": 51576,
+  " politique": 51485,
+  " pour": 50598,
+  " pr": 51190,
+  " pres": 52242,
+  " president": 51959,
+  " pri": 52371,
+  " pro": 51904,
+  " projet": 50663,
+  " prs": 52354,
+  " prsident": 51976,
+  " pub": 50923,
+  " q": 51896,
+  " qu": 51228,
+  " que": 51631,
+  " qui": 51201,
+  " r": 50428,
+  " ra": 52212,
+  " rab": 51206,
+  " rabi": 51296,
+  " raby": 50324,
+  " rachwa": 51350,
+  " rad": 50932,
+  " rades": 50350,
+  " rah": 50449,
+  " rahi": 51887,
+  " raho": 50631,
+  " rahom": 51339,
+  " rahou": 51780,
+  " raiis": 51940,
+  " rais": 50904,
+  " raj": 51199,
+  " raja": 50701,
+  " rajel": 50412,
+  " raji": 51033,
+  " rajil": 52091,
+  " rak": 52286,
+  " rakom": 50641,
+  " ram": 52460,
+  " rana": 51719,
+  " rani": 51349,
+  " rap": 50718,
+  " ras": 50972,
+  " raw": 50744,
+  " ray": 50741,
+  " rcd": 52362,
+  " re": 50818,
+  " recr": 51307,
+  " rej": 51769,
+  " res": 51497,
+  " respe": 51432,
+  " respect": 51274,
+  " ret": 51266,
+  " ri": 51748,
+  " ria": 51594,
+  " rie": 51627,
+  " riya": 51824,
+  " rja": 51536,
+  " rjal": 52248,
+  " rjel": 51890,
+  " ro": 50665,
+  " rod": 51446,
+  " rom": 50432,
+  " rou": 50731,
+  " rouh": 50814,
+  " rouhek": 52175,
+  " rouhou": 51010,
+  " rous": 50526,
+  " rwa": 50576,
+  " rwe": 52374,
+  " rya": 51866,
+  " rye": 51701,
+  " s": 51595,
+  " sa": 52512,
+  " sab": 51771,
+  " saber": 52412,
+  " sad": 52442,
+  " saf": 51654,
+  " sah": 51371,
+  " saha": 50679,
+  " sahbi": 50726,
+  " said": 51119,
+  " sais": 51391,
+  " sak": 50802,
+  " sal": 51037,
+  " sala": 51444,
+  " sam": 52168,
+  " sami": 51590,
+  " san": 52170,
+  " sanfara": 51293,
+  " sar": 52469,
+  " sare": 51461,
+  " saw": 50493,
+  " say": 51460,
+  " sayeb": 51684,
+  " sayed": 51466,
+  " se": 50777,
+  " seb": 51401,
+  " sel": 52012,
+  " ser": 51967,
+  " sera": 51075,
+  " sey": 50557,
+  " sfax": 50411,
+  " sh": 51879,
+  " shi": 50462,
+  " shih": 52267,
+  " si": 50750,
+  " sid": 52204,
+  " sidek": 50321,
+  " sidi": 50843,
+  " signa": 51500,
+  " signaler": 50394,
+  " sil": 50395,
+  " sin": 51532,
+  " sir": 51997,
+  " siya": 51596,
+  " siyes": 50276,
+  " sl": 50695,
+  " sli": 52474,
+  " slim": 52416,
+  " sma": 50823,
+  " sn": 51862,
+  " sna": 50766,
+  " snin": 52433,
+  " so": 50779,
+  " sob": 52398,
+  " sol": 51094,
+  " som": 51931,
+  " son": 52178,
+  " sor": 52356,
+  " sou": 50773,
+  " sour": 50878,
+  " sraf": 52522,
+  " st": 51002,
+  " sta": 51109,
+  " stade": 52199,
+  " star": 50573,
+  " stp": 51301,
+  " su": 52326,
+  " suis": 51222,
+  " sur": 51549,
+  " surtout": 51416,
+  " svp": 51459,
+  " sy": 51360,
+  " t": 51711,
+  " ta": 50536,
+  " tab": 50851,
+  " tach": 50262,
+  " tad": 50658,
+  " taf": 51615,
+  " tah": 50378,
+  " tahan": 51586,
+  " tahana": 50593,
+  " tahiya": 50585,
+  " tahki": 50962,
+  " tak": 51679,
+  " tal": 50376,
+  " tala": 50896,
+  " tam": 52272,
+  " tan": 50498,
+  " tar": 50827,
+  " taraj": 51160,
+  " taraji": 50979,
+  " tarajit": 50653,
+  " tari": 51334,
+  " tarja": 52118,
+  " tas": 51154,
+  " tat": 50389,
+  " taw": 51662,
+  " tay": 51619,
+  " taya": 51990,
+  " tayara": 50646,
+  " tb": 50885,
+  " tbar": 51881,
+  " tbi": 52018,
+  " tcha": 50406,
+  " tched": 51425,
+  " tchouf": 51980,
+  " te": 52274,
+  " teb": 50988,
+  " tech": 52485,
+  " techri": 51640,
+  " tef": 50871,
+  " tefhem": 51121,
+  " teh": 52167,
+  " tej": 52132,
+  " tek": 50863,
+  " tel": 51885,
+  " temchi": 50367,
+  " ten": 52440,
+  " ter": 51029,
+  " tes": 52515,
+  " tet": 50508,
+  " tf": 50446,
+  " tfa": 50747,
+  " tfo": 50296,
+  " tfou": 52055,
+  " tfouh": 50847,
+  " tg": 52056,
+  " th": 50854,
+  " tha": 50729,
+  " thab": 51476,
+  " thama": 51924,
+  " thar": 50419,
+  " thawra": 52295,
+  " the": 50707,
+  " theb": 50612,
+  " thez": 52479,
+  " thi": 50845,
+  " ti": 50561,
+  " tiit": 51019,
+  " tir": 51648,
+  " tis": 51064,
+  " tit": 50816,
+  " titre": 51898,
+  " tji": 51468,
+  " tjib": 51729,
+  " tk": 52099,
+  " tka": 51140,
+  " tkoun": 50713,
+  " tl": 51248,
+  " tla": 51263,
+  " tma": 51342,
+  " tn": 50512,
+  " tna": 52483,
+  " tnaj": 52232,
+  " tnajem": 50844,
+  " tnik": 52249,
+  " to": 50650,
+  " tofla": 50302,
+  " toi": 52330,
+  " ton": 51741,
+  " tones": 50424,
+  " top": 51227,
+  " tor": 51880,
+  " tos": 51723,
+  " tou": 51616,
+  " toul": 51237,
+  " toun": 51779,
+  " tounes": 52518,
+  " tounis": 50290,
+  " touns": 52275,
+  " tounsi": 51218,
+  " tous": 51799,
+  " tout": 51567,
+  " tr": 52133,
+  " tra": 50756,
+  " trab": 51326,
+  " trabel": 51042,
+  " travail": 51120,
+  " travailler": 50712,
+  " tri": 51385,
+  " tro": 52019,
+  " trs": 52500,
+  " ts": 51742,
+  " tsa": 50273,
+  " tt": 51455,
+  " tu": 51730,
+  " tun": 52493,
+  " tunis": 51159,
+  " tunisi": 52268,
+  " tunisie": 51653,
+  " tunisien": 51048,
+  " tv": 51395,
+  " tw": 51346,
+  " twa": 50755,
+  " twali": 51603,
+  " twalli": 51027,
+  " twansa": 50492,
+  " twensa": 51544,
+  " ty": 50670,
+  " tzid": 51753,
+  " u": 51289,
+  " un": 51629,
+  " une": 51066,
+  " up": 52494,
+  " v": 52202,
+  " va": 50545,
+  " ve": 51865,
+  " ver": 52097,
+  " veut": 50632,
+  " vi": 50600,
+  " video": 51831,
+  " vido": 52508,
+  " vive": 52214,
+  " vo": 51644,
+  " vot": 50284,
+  " vous": 52379,
+  " vraiment": 51685,
+  " vu": 51076,
+  " w": 50299,
+  " wa": 51964,
+  " wach": 52505,
+  " wadh": 52507,
+  " wah": 51448,
+  " wahda": 50812,
+  " wahed": 51392,
+  " wahid": 50930,
+  " wahna": 51172,
+  " wak": 50973,
+  " waka": 51839,
+  " wakil": 50801,
+  " wakt": 52465,
+  " wal": 50834,
+  " walah": 50659,
+  " walahi": 52124,
+  " waldik": 51308,
+  " walet": 51641,
+  " walh": 52028,
+  " wali": 52164,
+  " walid": 51399,
+  " walit": 51622,
+  " walla": 50452,
+  " wallahi": 52171,
+  " wan": 52458,
+  " wana": 51525,
+  " war": 52190,
+  " was": 51424,
+  " wasel": 51006,
+  " wat": 50853,
+  " watani": 50455,
+  " wb": 52041,
+  " wba": 50621,
+  " wch": 51093,
+  " wcha": 51991,
+  " we": 52321,
+  " web": 52153,
+  " wech": 51689,
+  " wed": 51659,
+  " weh": 50309,
+  " wehed": 52108,
+  " wej": 52101,
+  " wek": 51664,
+  " wel": 50634,
+  " wela": 51013,
+  " weld": 51270,
+  " weldi": 51205,
+  " weldik": 50937,
+  " weli": 50292,
+  " wella": 51776,
+  " welli": 50427,
+  " wem": 51937,
+  " wen": 51905,
+  " wena": 51526,
+  " went": 51256,
+  " wenta": 51157,
+  " wenti": 52318,
+  " wentouma": 50349,
+  " wer": 50542,
+  " wes": 51186,
+  " wet": 50311,
+  " wfi": 52066,
+  " wh": 50739,
+  " wha": 51808,
+  " wi": 51559,
+  " wil": 51106,
+  " wila": 50886,
+  " wild": 51242,
+  " wili": 50263,
+  " win": 50334,
+  " wini": 50430,
+  " winou": 50769,
+  " winti": 51233,
+  " wis": 52142,
+  " wit": 52094,
+  " wj": 51735,
+  " wjou": 51591,
+  " wk": 51021,
+  " wken": 52088,
+  " wkol": 51454,
+  " wl": 51182,
+  " wla": 52221,
+  " wlad": 51247,
+  " wle": 50997,
+  " wled": 52241,
+  " wli": 51016,
+  " wm": 51618,
+  " wma": 51135,
+  " wn": 51047,
+  " wna": 50599,
+  " wo": 50994,
+  " wou": 50909,
+  " wra": 51767,
+  " wrabi": 50556,
+  " wrak": 52119,
+  " ws": 51074,
+  " wt": 51833,
+  " wta": 52386,
+  " wy": 51929,
+  " wya": 51849,
+  " wzid": 52106,
+  " y": 51419,
+  " ya": 51999,
+  " yab": 50614,
+  " yach": 51001,
+  " yad": 51212,
+  " yaf": 50993,
+  " yah": 52228,
+  " yahdik": 50783,
+  " yahki": 50515,
+  " yak": 52098,
+  " yakhi": 51379,
+  " yal": 51496,
+  " yam": 51134,
+  " yan": 51148,
+  " yar": 50911,
+  " yarab": 50288,
+  " yarham": 52314,
+  " yarja": 51057,
+  " yas": 52431,
+  " yat": 51842,
+  " yatla": 50346,
+  " ycha": 52447,
+  " yched": 51276,
+  " yda": 52486,
+  " ye": 52040,
+  " yeb": 52302,
+  " yech": 51137,
+  " yed": 50555,
+  " yef": 51869,
+  " yefhem": 52238,
+  " yeh": 51907,
+  " yej": 51996,
+  " yek": 50640,
+  " yekhdem": 51600,
+  " yekhi": 52336,
+  " yel": 52083,
+  " yelz": 52036,
+  " yelzem": 51745,
+  " yem": 52054,
+  " yemchi": 50319,
+  " yen": 51196,
+  " yer": 51486,
+  " yes": 52243,
+  " yeser": 52215,
+  " yesser": 52487,
+  " yesta": 51966,
+  " yet": 52457,
+  " yez": 50285,
+  " yezi": 50274,
+  " yezzi": 52246,
+  " yf": 51823,
+  " yh": 51621,
+  " yheb": 51150,
+  " yhez": 52530,
+  " yi": 51569,
+  " yil": 51724,
+  " yit": 52277,
+  " yj": 52226,
+  " yji": 51970,
+  " yjib": 50790,
+  " yk": 50919,
+  " ykoun": 50329,
+  " yn": 51922,
+  " yna": 51406,
+  " ynik": 51153,
+  " yo": 51031,
+  " yod": 50765,
+  " yon": 51479,
+  " yos": 52283,
+  " you": 51965,
+  " youm": 50625,
+  " yous": 51282,
+  " youtu": 51519,
+  " youtube": 51722,
+  " yr": 52217,
+  " ys": 52075,
+  " ysa": 50377,
+  " yt": 51464,
+  " yta": 50703,
+  " ywa": 50706,
+  " ywaf": 51702,
+  " ywali": 52376,
+  " yzid": 51477,
+  " z": 51489,
+  " za": 52527,
+  " zab": 51315,
+  " zabour": 50819,
+  " zada": 51440,
+  " zah": 51522,
+  " zan": 50384,
+  " zantour": 50692,
+  " zar": 50914,
+  " zaw": 50810,
+  " zawali": 52024,
+  " zay": 51364,
+  " zayed": 51003,
+  " zbou": 50501,
+  " zboubna": 51054,
+  " ze": 51650,
+  " zeb": 51638,
+  " zebbi": 51378,
+  " zebi": 51908,
+  " zeby": 50642,
+  " zed": 51955,
+  " zeda": 50764,
+  " zey": 51405,
+  " zeyed": 51139,
+  " zi": 51548,
+  " zid": 51927,
+  " zin": 50969,
+  " zina": 52497,
+  " zok": 51175,
+  " zou": 51851,
+  " zouz": 50840,
+  "aak": 51320,
+  "abd": 52046,
+  "abed": 51180,
+  "abes": 52020,
+  "adch": 50271,
+  "adech": 52114,
+  "adek": 51695,
+  "adha": 50652,
+  "adich": 52146,
+  "adna": 51636,
+  "afila": 52090,
+  "afou": 51130,
+  "afsa": 51142,
+  "ahba": 51818,
+  "aher": 52135,
+  "ahla": 52369,
+  "ahna": 50611,
+  "ahom": 51888,
+  "ajet": 51555,
+  "akber": 50776,
+  "akom": 51838,
+  "alah": 50888,
+  "alb": 52045,
+  "albi": 50601,
+  "alek": 51078,
+  "alem": 52025,
+  "alet": 51281,
+  "alha": 50277,
+  "alih": 50306,
+  "aliha": 50662,
+  "alik": 51617,
+  "alil": 51736,
+  "alim": 51550,
+  "alina": 52285,
+  "alit": 51303,
+  "aliya": 50522,
+  "alleb": 51383,
+  "allem": 51132,
+  "allou": 50793,
+  "alou": 52000,
+  "alta": 50916,
+  "alya": 52280,
+  "amal": 52062,
+  "amej": 51204,
+  "amem": 51571,
+  "amil": 51995,
+  "amla": 50645,
+  "amlet": 51936,
+  "amlin": 51380,
+  "amlou": 52154,
+  "amma": 50487,
+  "amra": 51983,
+  "andek": 50943,
+  "andha": 51058,
+  "andhom": 51166,
+  "andik": 50297,
+  "andk": 51731,
+  "andkom": 50423,
+  "andna": 50603,
+  "andou": 51829,
+  "andouk": 51007,
+  "anet": 51504,
+  "anoun": 51972,
+  "ansa": 51846,
+  "arab": 51267,
+  "arar": 50551,
+  "arbi": 51179,
+  "archa": 50657,
+  "aref": 52316,
+  "arej": 51337,
+  "arek": 51933,
+  "arjou": 52360,
+  "asba": 51441,
+  "assa": 51341,
+  "assba": 50286,
+  "atik": 50738,
+  "atir": 51478,
+  "atr": 51633,
+  "atrou": 51588,
+  "awali": 51377,
+  "awel": 50666,
+  "awen": 50564,
+  "awla": 50925,
+  "awnou": 50815,
+  "awra": 50893,
+  "aych": 51610,
+  "ayeb": 51244,
+  "ayech": 51230,
+  "ayel": 52478,
+  "ayla": 50570,
+  "bab": 50540,
+  "baba": 51918,
+  "bak": 50724,
+  "barek": 52405,
+  "barra": 52209,
+  "beb": 51286,
+  "bech": 52297,
+  "belahi": 52517,
+  "belehi": 50511,
+  "beli": 51480,
+  "bellahi": 51836,
+  "bellehi": 50518,
+  "bha": 51219,
+  "bien": 52210,
+  "bih": 51414,
+  "bik": 51587,
+  "bikom": 52059,
+  "billehi": 51329,
+  "bina": 51085,
+  "bir": 50267,
+  "bira": 51039,
+  "biya": 51283,
+  "bjeh": 50326,
+  "bk": 50336,
+  "bla": 51657,
+  "bna": 51855,
+  "bonne": 51351,
+  "bou": 52435,
+  "boub": 51971,
+  "bouch": 50821,
+  "bouh": 51813,
+  "bouha": 50366,
+  "bouk": 51305,
+  "boul": 51347,
+  "bouna": 52523,
+  "boura": 51895,
+  "boutoula": 51318,
+  "brabbi": 51362,
+  "bras": 52082,
+  "brok": 50330,
+  "brou": 52003,
+  "bsara": 50633,
+  "bya": 50913,
+  "cain": 52096,
+  "cef": 50562,
+  "chala": 50787,
+  "chalah": 50371,
+  "chalh": 51165,
+  "challa": 51612,
+  "challah": 50507,
+  "chay": 50553,
+  "chbik": 52017,
+  "chir": 50884,
+  "chnowa": 51355,
+  "chof": 52427,
+  "chok": 50958,
+  "chou": 51084,
+  "chouf": 52381,
+  "choufou": 52396,
+  "chwa": 50952,
+  "cou": 51834,
+  "cteur": 52237,
+  "dak": 51514,
+  "daw": 50751,
+  "dawla": 51202,
+  "dech": 51798,
+  "dek": 51491,
+  "dha": 51585,
+  "dhaf": 51949,
+  "dhar": 51981,
+  "dheb": 52103,
+  "dher": 51575,
+  "dhi": 51472,
+  "dhif": 51035,
+  "dhou": 51765,
+  "dia": 50535,
+  "dik": 52102,
+  "dima": 50788,
+  "dina": 50852,
+  "dine": 51871,
+  "dmo": 50860,
+  "dmou": 51138,
+  "dna": 50936,
+  "dou": 50315,
+  "douh": 52196,
+  "douk": 51306,
+  "doul": 52400,
+  "ebe": 52407,
+  "ebek": 52481,
+  "ebha": 51882,
+  "ebi": 50903,
+  "ebo": 50546,
+  "ebou": 51794,
+  "echa": 51626,
+  "eche": 50269,
+  "edh": 52480,
+  "edma": 50889,
+  "edou": 52115,
+  "eek": 50697,
+  "efi": 51277,
+  "eflous": 51772,
+  "eha": 51597,
+  "ehi": 51506,
+  "ehom": 52233,
+  "ehri": 51652,
+  "ej": 51956,
+  "eji": 51386,
+  "ekel": 51086,
+  "ekh": 50917,
+  "ekom": 50708,
+  "elet": 50592,
+  "elha": 50583,
+  "elhom": 50705,
+  "elkom": 51151,
+  "elna": 50364,
+  "elou": 51766,
+  "emchi": 50800,
+  "enchallah": 50753,
+  "ensa": 52029,
+  "enti": 52205,
+  "enya": 51607,
+  "etek": 50620,
+  "etha": 50742,
+  "ethom": 50453,
+  "etna": 51760,
+  "etou": 51696,
+  "eya": 50651,
+  "eyet": 50568,
+  "fach": 52253,
+  "fad": 51188,
+  "fak": 51592,
+  "fama": 50687,
+  "fara": 50926,
+  "faraj": 50442,
+  "farej": 51942,
+  "farjou": 51259,
+  "fek": 50531,
+  "fel": 50974,
+  "fes": 50931,
+  "fici": 51189,
+  "ficiel": 50850,
+  "fih": 52364,
+  "fiha": 51989,
+  "fik": 51930,
+  "fir": 50856,
+  "fla": 50857,
+  "flous": 52111,
+  "fou": 51245,
+  "fouh": 51487,
+  "fri": 51511,
+  "ghar": 51560,
+  "ghi": 51950,
+  "ghir": 50548,
+  "gla": 51713,
+  "gna": 52189,
+  "gol": 50392,
+  "gou": 51598,
+  "goul": 50966,
+  "habet": 50927,
+  "hach": 50947,
+  "hada": 52519,
+  "hadha": 50579,
+  "hadi": 51198,
+  "haf": 51923,
+  "hah": 50379,
+  "haha": 52057,
+  "hahah": 51707,
+  "hahaha": 51601,
+  "hahahaha": 50950,
+  "hallah": 51036,
+  "hamed": 50268,
+  "hana": 50953,
+  "hata": 51605,
+  "hawra": 51251,
+  "hay": 51910,
+  "haya": 51743,
+  "haz": 51445,
+  "hb": 50859,
+  "hba": 50441,
+  "hdem": 51678,
+  "heb": 52070,
+  "hebou": 51474,
+  "hech": 51732,
+  "hedha": 50722,
+  "hedhi": 50559,
+  "hek": 51984,
+  "heka": 52031,
+  "hez": 51945,
+  "hia": 51014,
+  "hich": 52292,
+  "hih": 51994,
+  "hihi": 50870,
+  "hil": 52134,
+  "hir": 51129,
+  "hiya": 51820,
+  "hkom": 52161,
+  "hmou": 50961,
+  "homa": 51726,
+  "homch": 51451,
+  "houch": 52426,
+  "houm": 51363,
+  "houma": 52095,
+  "houwa": 51919,
+  "howa": 50920,
+  "ibou": 51853,
+  "icha": 50317,
+  "ichou": 51387,
+  "idek": 51396,
+  "idh": 51757,
+  "idha": 52498,
+  "idin": 51051,
+  "idma": 51356,
+  "iha": 51070,
+  "iin": 51845,
+  "iir": 51868,
+  "iis": 51699,
+  "iit": 51579,
+  "ikom": 50934,
+  "ilhom": 50954,
+  "ilna": 51473,
+  "ilou": 52188,
+  "imchi": 52022,
+  "inchalah": 51239,
+  "inek": 52394,
+  "inik": 51152,
+  "inou": 51540,
+  "inta": 51762,
+  "inu": 51063,
+  "irou": 50460,
+  "issi": 51721,
+  "itek": 51358,
+  "itha": 51810,
+  "itna": 51962,
+  "itou": 50968,
+  "iwar": 51131,
+  "iyet": 50298,
+  "jal": 51045,
+  "jaw": 51469,
+  "jb": 51961,
+  "jbou": 50725,
+  "jbouj": 50497,
+  "jeb": 51920,
+  "jebni": 51806,
+  "jeh": 50716,
+  "jel": 51499,
+  "jem": 50868,
+  "jh": 51304,
+  "jib": 50354,
+  "jibou": 50831,
+  "jich": 51117,
+  "jil": 51344,
+  "jla": 50260,
+  "joli": 50435,
+  "jom": 50876,
+  "jomhour": 50906,
+  "jou": 52068,
+  "joulia": 52499,
+  "jouliya": 51704,
+  "jour": 51055,
+  "jr": 51492,
+  "kach": 50479,
+  "kad": 52186,
+  "kal": 51787,
+  "kalb": 51241,
+  "kalem": 51381,
+  "kallah": 51022,
+  "kam": 52491,
+  "kaw": 52366,
+  "kayet": 52158,
+  "kch": 51183,
+  "kek": 50504,
+  "kem": 50660,
+  "keya": 52403,
+  "keyet": 51911,
+  "kha": 51768,
+  "khal": 51215,
+  "khali": 52482,
+  "khi": 50282,
+  "kich": 52430,
+  "kif": 50470,
+  "kila": 51624,
+  "kim": 50803,
+  "kina": 50710,
+  "kir": 52335,
+  "kira": 52338,
+  "kiw": 51114,
+  "kla": 50489,
+  "klay": 50414,
+  "klem": 51493,
+  "kol": 52229,
+  "kolna": 50905,
+  "kom": 51116,
+  "kon": 50454,
+  "kont": 51582,
+  "kou": 50688,
+  "koul": 52061,
+  "koum": 50418,
+  "kouma": 51158,
+  "koun": 52466,
+  "koura": 52143,
+  "krou": 50496,
+  "lach": 51331,
+  "laha": 51758,
+  "lahi": 51856,
+  "lak": 52409,
+  "lal": 51217,
+  "layhi": 51558,
+  "leb": 51083,
+  "lech": 50408,
+  "lef": 52333,
+  "leh": 51891,
+  "leha": 50448,
+  "lehi": 51169,
+  "lek": 50415,
+  "lel": 50587,
+  "leya": 50340,
+  "leybi": 50789,
+  "lh": 51815,
+  "lha": 50610,
+  "lhi": 51951,
+  "lhom": 51830,
+  "lih": 52303,
+  "liha": 52294,
+  "lihom": 51136,
+  "likom": 52370,
+  "lil": 50514,
+  "lina": 51319,
+  "liya": 51104,
+  "lk": 52184,
+  "lkol": 51226,
+  "lkom": 51210,
+  "lm": 50342,
+  "lna": 51411,
+  "lob": 51017,
+  "lool": 52451,
+  "lou": 50678,
+  "loub": 50654,
+  "loubna": 50867,
+  "louch": 50357,
+  "louh": 52187,
+  "loul": 52417,
+  "loum": 52468,
+  "louma": 52086,
+  "lous": 51593,
+  "lub": 51156,
+  "lz": 52504,
+  "maak": 50382,
+  "macha": 51692,
+  "maf": 51602,
+  "mah": 51112,
+  "mais": 51163,
+  "maj": 50990,
+  "mak": 50318,
+  "malla": 51578,
+  "malt": 51475,
+  "maltou": 51877,
+  "mana": 50623,
+  "mara": 51666,
+  "marzou": 50965,
+  "mch": 51915,
+  "mchi": 50754,
+  "mech": 51683,
+  "mej": 51234,
+  "mek": 51333,
+  "mela": 50661,
+  "merci": 52448,
+  "mha": 50413,
+  "mij": 52467,
+  "mik": 50363,
+  "mla": 52144,
+  "mlo": 50607,
+  "mlou": 52042,
+  "mna": 50312,
+  "moch": 51426,
+  "mou": 51193,
+  "mouch": 51050,
+  "mour": 52265,
+  "mout": 50331,
+  "moutou": 51821,
+  "naf": 50915,
+  "naha": 52128,
+  "nahda": 51554,
+  "nahdha": 50647,
+  "naj": 50577,
+  "najem": 51503,
+  "najmou": 51744,
+  "nak": 50351,
+  "namej": 52524,
+  "natir": 51145,
+  "nawa": 52390,
+  "naya": 51090,
+  "nch": 51292,
+  "nech": 50541,
+  "neha": 50717,
+  "nek": 51155,
+  "nem": 52443,
+  "neya": 51366,
+  "nheb": 51438,
+  "nich": 50343,
+  "nina": 50609,
+  "niya": 51278,
+  "nk": 52194,
+  "nou": 51185,
+  "noua": 50770,
+  "nous": 52121,
+  "nouwa": 50986,
+  "nowa": 51926,
+  "nya": 52127,
+  "obravo": 50999,
+  "odem": 50939,
+  "odret": 50558,
+  "odwa": 51261,
+  "okh": 50368,
+  "okom": 51523,
+  "olek": 50837,
+  "olha": 52105,
+  "olik": 51921,
+  "olna": 51761,
+  "olou": 50897,
+  "omra": 52257,
+  "omri": 52255,
+  "omrou": 52313,
+  "onc": 51272,
+  "oncef": 52195,
+  "oneya": 52060,
+  "oua": 52346,
+  "ouba": 50270,
+  "oubi": 51822,
+  "ouh": 50494,
+  "ouha": 52531,
+  "oui": 50825,
+  "oukouma": 52317,
+  "oula": 51264,
+  "ouled": 52219,
+  "oulna": 51402,
+  "oulou": 51482,
+  "oum": 50861,
+  "ouma": 52071,
+  "ouna": 52235,
+  "oune": 52001,
+  "ouni": 52399,
+  "ounsi": 51101,
+  "oura": 51354,
+  "oussa": 51884,
+  "ouya": 50434,
+  "patron": 50804,
+  "pf": 50305,
+  "qui": 51483,
+  "quipe": 50465,
+  "raba": 50481,
+  "rabbi": 50829,
+  "rabi": 50353,
+  "rach": 50422,
+  "racha": 51978,
+  "raha": 50976,
+  "rai": 51539,
+  "raiment": 50728,
+  "rais": 51803,
+  "raj": 50955,
+  "raja": 50503,
+  "rajel": 50635,
+  "raji": 52382,
+  "rajil": 51599,
+  "rana": 50602,
+  "rasmi": 51675,
+  "rass": 52516,
+  "ravail": 52177,
+  "ravo": 51809,
+  "rej": 50365,
+  "rfou": 52475,
+  "rhou": 51847,
+  "riba": 51513,
+  "rif": 50310,
+  "rij": 51357,
+  "riki": 52104,
+  "rima": 50942,
+  "riya": 51874,
+  "rj": 50482,
+  "roj": 51975,
+  "rouf": 50996,
+  "rouh": 51258,
+  "sab": 51096,
+  "sad": 50447,
+  "sah": 50457,
+  "sak": 51225,
+  "sami": 51944,
+  "sar": 52363,
+  "sara": 51848,
+  "sawer": 51449,
+  "sayeb": 50771,
+  "sayer": 51954,
+  "sba": 51837,
+  "seb": 50898,
+  "sek": 52429,
+  "sia": 51917,
+  "sib": 50786,
+  "sieur": 50796,
+  "sif": 51747,
+  "sion": 51214,
+  "sir": 52421,
+  "siya": 51535,
+  "sma": 50669,
+  "snin": 52201,
+  "sou": 50616,
+  "soub": 51542,
+  "ssa": 52441,
+  "ssar": 52391,
+  "sse": 52149,
+  "ssek": 50258,
+  "ssel": 50477,
+  "ssem": 51407,
+  "ssen": 51490,
+  "sser": 50912,
+  "ssi": 50581,
+  "ssir": 50615,
+  "ssou": 50358,
+  "svp": 52359,
+  "taf": 50308,
+  "tah": 50525,
+  "tak": 50799,
+  "tala": 52495,
+  "tali": 50529,
+  "tam": 51537,
+  "tama": 52437,
+  "tana": 51583,
+  "tani": 52245,
+  "tat": 51208,
+  "tation": 50838,
+  "taw": 51543,
+  "tawa": 50604,
+  "taz": 52172,
+  "teb": 50500,
+  "teh": 51100,
+  "tena": 51030,
+  "tet": 50490,
+  "teur": 51255,
+  "thar": 51348,
+  "thi": 51394,
+  "thom": 52438,
+  "thou": 50480,
+  "tia": 51943,
+  "tich": 51043,
+  "tih": 50778,
+  "tik": 50488,
+  "tikom": 51770,
+  "tina": 52339,
+  "tini": 50685,
+  "tique": 51792,
+  "tir": 51115,
+  "tira": 50794,
+  "tiram": 52461,
+  "tit": 52074,
+  "tiya": 51252,
+  "tla": 52387,
+  "tna": 50582,
+  "tni": 51098,
+  "tou": 50425,
+  "touh": 51660,
+  "touha": 51181,
+  "toula": 51023,
+  "touma": 52247,
+  "toun": 52311,
+  "touna": 52306,
+  "tounes": 51430,
+  "tounis": 51032,
+  "tour": 50362,
+  "tout": 52284,
+  "tunis": 50289,
+  "tyle": 52023,
+  "unis": 50637,
+  "ussi": 52222,
+  "veau": 51844,
+  "vot": 50433,
+  "vraiment": 51914,
+  "waf": 50471,
+  "wah": 51143,
+  "wak": 51011,
+  "walah": 51749,
+  "walahi": 52365,
+  "wali": 52323,
+  "walli": 51404,
+  "wawla": 51088,
+  "waya": 52496,
+  "weh": 52173,
+  "wej": 51568,
+  "wel": 51805,
+  "wensa": 51467,
+  "wenti": 50400,
+  "wet": 51312,
+  "wewla": 50519,
+  "wira": 50874,
+  "wiya": 52261,
+  "wla": 50437,
+  "wled": 50552,
+  "wna": 52231,
+  "yab": 51693,
+  "yahi": 51746,
+  "yak": 51122,
+  "yar": 52138,
+  "yara": 52464,
+  "yarat": 51415,
+  "yarhmou": 52300,
+  "yat": 51913,
+  "yeb": 51963,
+  "yech": 51563,
+  "yed": 52445,
+  "yeh": 50734,
+  "yehi": 50748,
+  "yek": 51574,
+  "yen": 51691,
+  "yena": 52310,
+  "yez": 51538,
+  "yh": 51577,
+  "yin": 52290,
+  "youm": 51273,
+  "youma": 51528,
+  "youn": 51200,
+  "yya": 52048,
+  "zab": 52348,
+  "zah": 51541,
+  "zarti": 51774,
+  "zay": 52126,
+  "zem": 52251,
+  "zet": 51625,
+  "zid": 50760,
+  "zim": 52298,
+  "zina": 51220,
+  "zir": 52471,
+  "ziz": 50824,
+  "zou": 50505,
+  "zouza": 51843
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}